Learned Construction Grammars Converge Across Registers Given Increased Exposure

Jonathan Dunn, Harish Tayyar Madabushi


Abstract
This paper measures the impact of increased exposure on whether learned construction grammars converge onto shared representations when trained on data from different registers. Register influences the frequency of constructions, with some structures common in formal but not informal usage. We expect that a grammar induction algorithm exposed to different registers will acquire different constructions. To what degree does increased exposure lead to the convergence of register-specific grammars? The experiments in this paper simulate language learning in 12 languages (half Germanic and half Romance) with corpora representing three registers (Twitter, Wikipedia, Web). These simulations are repeated with increasing amounts of exposure, from 100k to 2 million words, to measure the impact of exposure on the convergence of grammars. The results show that increased exposure does lead to converging grammars across all languages. In addition, a shared core of register-universal constructions remains constant across increasing amounts of exposure.
Anthology ID:
2021.conll-1.21
Volume:
Proceedings of the 25th Conference on Computational Natural Language Learning
Month:
November
Year:
2021
Address:
Online
Venues:
CoNLL | EMNLP
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
268–278
Language:
URL:
https://aclanthology.org/2021.conll-1.21
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.conll-1.21.pdf